gate-check
Skill0 starsChanged 4 months agoMITView on GitHub
Use when validating readiness to advance to the next project phase, before major milestones, after completing a full sprint or epic, or when the designer asks 'are we ready to move on?' Spawns all 4 director agents in parallel for independent verdicts. ShiningPlague-adopted: project paths (docs/adr/ + {{GDD_PATH}} + data/_schemas/system_registry.json), review-mode (full/lean/solo) integration.
20 other projects use a version of this.
Adopted by
Most recently taken up by
- microsoft/cat-agent-skillstheir own version, first seen Nov 8, 2026
- striderZA/OpenCodeGameStudiostheir own version, first seen Nov 4, 2026
- supernovae-st/nikatheir own version, first seen Oct 28, 2026
- Donchitos/Claude-Code-Game-Studiostheir own version, first seen Oct 19, 2026
- venus2099/codex-game-studiostheir own version, first seen Oct 17, 2026
- nuncaeslupus/literary-critictheir own version, first seen Oct 13, 2026
Used with
Projects with it also use soak-test, team-live-ops and 1 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
lilangMaxSkillsoak-test
Generate a soak test protocol for extended play sessions. Defines what to observe, measure, and log during long play sessions to surface slow leaks, fatigue effects, and edge cases that only appear after sustained play. Primarily used in Polish and Release phases.
Also in 9 projects that use this
lilangMaxSkillteam-live-ops
Orchestrate the live-ops team for post-launch content planning: coordinates live-ops-designer, economy-designer, analytics-engineer, community-manager, writer, and narrative-director to design and plan a season, event, or live content update.
Also in 9 projects that use this
- +1 more from lilangMax
Other versions20 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 20
- Donchitos/Claude-Code-Game-Studios★ 27ksame name
- pixel-cellar/Claude-Code-Game-Studios★ 324same name
- striderZA/OpenCodeGameStudios★ 118same name
- microsoft/cat-agent-skills★ 101same name
- supernovae-st/nika★ 96same name
- tranhieutt/software_development_department★ 71same name
- cenconq25/claude-code-app-studio★ 40same name
- CoralGame/Claude-Code-Game-Studios★ 19same name
- phj128/autoworker★ 18same name
- dawn840705/codex-code-studios★ 17same name
10 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository68 other files it gives its agents.
- adoptSkill
- architecture-decisionSkill
- architecture-reviewSkill
- art-bibleSkill
- asset-specSkill
- brainstormingSkill
- bug-reportSkill
- bug-triageSkill
- code-reviewSkill
- consistency-checkSkill
- content-auditSkill
- create-architectureSkill
- create-control-manifestSkill
- create-epicsSkill
- create-storiesSkill
- day-one-patchSkill
- design-reviewSkill
- design-systemSkill
- dev-storySkill
- dispatching-parallel-agentsSkill
- estimateSkill
- executing-plansSkill
- finishing-a-development-branchSkill
- goal-add-minorSkill
- goal-checkSkill
- goal-setSkill
- godot-engineSkill
- helpSkill
- map-systemsSkill
- narrative-designerSkill
- project-stage-detectSkill
- propagate-design-changeSkill
- qa-planSkill
- quick-designSkill
- red-flag-scanSkill
- regression-suiteSkill
- retrospectiveSkill
- review-all-gddsSkill
- safety-pushSkill
- scope-checkSkill
- security-auditSkill
- session-closeSkill
- setup-engineSkill
- sprint-planSkill
- startSkill
- story-doneSkill
- story-readinessSkill
- subagent-driven-developmentSkill
- systematic-debuggingSkill
- team-artSkill
- team-audioSkill
- team-combatSkill
- team-economySkill
- team-infraSkill
- team-levelSkill
- team-marketingSkill
- team-narrativeSkill
- team-polishSkill
- team-releaseSkill
- team-securitySkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
12 rules. 0 are common, 6 are distinctive, and 6 are very specific to this project.
0
Common
Most of the 19 edited versions we read keep these.
6
Distinctive
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 35
If argument provided: use it as the target phase.
- Very specific: line 37
If no argument: read production/stage.txt for current phase, then propose next phase from sequence.
- Distinctive: line 47
Read silently before presenting anything:
- Very specific: line 75
If mode is solo: skip to Phase 5 (artifact-only check).
- Very specific: line 108
If required: true and artifact exists: PASS
- Very specific: line 109
If required: true and artifact missing: FAIL (blocker)
- Very specific: line 110
If required: false and artifact missing: NOTE (optional)
- Distinctive: line 119
All READY + all required artifacts present → eligible for PASS
- Distinctive: line 152
If composite verdict is PASS and designer confirms advancement:
- Very specific: line 153
Write target phase name to production/stage.txt
- Distinctive: line 156
If CONCERNS and designer chooses to accept:
- Distinctive: line 160
If FAIL: do NOT update stage.txt.
“Common” is measured: kept by at least 6 in 10 of the 19 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Gate Check — Phase Transition Validation
🌱 ShiningPlague-adopted. Originally Donchitos (barebones stub); battle-tested on a shipped Godot project. Upstream was a pointer-only file; the studio version is the full implementation — parallel director dispatch, artifact completeness check, composite verdict, stage.txt write.
Validates project readiness to advance from one phase to the next by spawning 4 director agents in parallel, each reviewing from their domain. Produces a composite PASS / CONCERNS / FAIL verdict.
If an artifact named here is absent: say so plainly in one line, skip that step, and continue. Never invent the file to satisfy a checklist, and never fail a close because an optional artifact was never created.
Phases (from workflow-catalog.yaml)
Concept → Systems Design → Technical Setup → Pre-Production → Production → Polish → Release
Phase 1: Determine Target Phase
If argument provided: use it as the target phase.
If no argument: read production/stage.txt for current phase, then propose next phase from sequence. Confirm with designer.
stage.txt is seeded not-started — that is not a phase, it means no gate has ever
passed here. Read it as "current phase: none" and propose concept as the target. This
skill's PASS is what writes the first real phase word into the file.
Phase 2: Collect Artifacts
Read silently before presenting anything:
production/stage.txt— current phaseproduction/review-mode.txt— resolve review mode (full/lean/solo)docs/gdd/systems-index.md— systems status overviewdocs/architecture/tr-registry.yaml— requirement coveragedocs/architecture/control-manifest.md— programmer rules compliancedata/_schemas/system_registry.json— authoritative system states- Glob
docs/adr/[0-9]*.md— all ADRs and statuses - Glob
docs/gdd/*.md+{{GDD_PATH}}— all GDD artifacts - Glob
production/sprints/sprint-*.md— sprint artifacts (if any) - Glob
production/session-logs/playtest-*.md— playtest notes written by/qa-plan(if any)
Project path adaptations:
- ADRs at
docs/adr/(docs/architecture/holds the blueprint + manifest, never ADRs) - Master GDD at
{{GDD_PATH}}(if not split per-system yet) - System status from
data/_schemas/system_registry.json(authoritative) - Design specs at
docs/specs/, plans atdocs/plans/
Phase 3: Resolve Review Mode
Read production/review-mode.txt. Apply:
- full — spawn all 4 director gates (default)
- lean — spawn PHASE-GATEs only (this IS a phase gate, so all 4 run anyway)
- solo — skip all gates, just do artifact checks, report directly
If mode is solo: skip to Phase 5 (artifact-only check).
Phase 4: Spawn Director Gates (parallel)
Spawn ALL 4 director agents simultaneously via Agent tool. Issue all calls before waiting for any result.
Reference: .claude/docs/director-gates.md for full gate prompts.
Gate 1: CD-PHASE-GATE (creative-director)
Pass: target phase, all artifact paths, game pillars from {{GDD_PATH}} pillars section, core fantasy. Verdict: READY / CONCERNS / NOT READY
Gate 2: TD-PHASE-GATE (technical-director)
Pass: target phase, architecture doc path (if exists), engine reference, ADR list. Verdict: READY / CONCERNS / NOT READY
Gate 3: PR-PHASE-GATE (producer)
Pass: target phase, sprint/milestone artifacts, team size (solo), blocked story count. Verdict: READY / CONCERNS / NOT READY
Gate 4: AD-PHASE-GATE (art-director)
Pass: target phase, all art/visual artifacts, art bible (if exists). Verdict: READY / CONCERNS / NOT READY
Phase 5: Artifact Completeness Check
Independently of director verdicts, check the target phase's required artifacts from workflow-catalog.yaml:
For each step in target phase:
- If
required: trueand artifact exists: PASS - If
required: trueand artifact missing: FAIL (blocker) - If
required: falseand artifact missing: NOTE (optional)
Phase 6: Composite Verdict
Apply escalation rules:
- Any NOT READY / REJECT from directors → overall FAIL
- Any CONCERNS from directors → overall CONCERNS
- All READY + all required artifacts present → eligible for PASS
- One FAIL artifact check overrides all READY directors → FAIL
Present composite verdict with per-director breakdown:
## Gate Check: [Current Phase] → [Target Phase]
**Composite Verdict: [PASS / CONCERNS / FAIL]**
| Director | Verdict | Key Finding |
|----------|---------|-------------|
| Creative Director | READY | [one-line summary] |
| Technical Director | CONCERNS | [one-line summary] |
| Producer | READY | [one-line summary] |
| Art Director | NOT READY | [one-line summary] |
### Artifact Check
- [x] [required artifact] — present
- [ ] [required artifact] — MISSING (blocker)
- [-] [optional artifact] — not present (advisory)
### Director Concerns (if any)
[Full text of each CONCERNS or NOT READY verdict]
### Recommendation
[Specific next actions to address blockers or concerns]Phase 7: Write Stage File (if PASS)
If composite verdict is PASS and designer confirms advancement:
- Write target phase name to
production/stage.txt - Note: "Phase advanced to [target phase] on [date]"
If CONCERNS and designer chooses to accept:
- Write target phase name to
production/stage.txt - Append: "Advanced with accepted concerns on [date]"
If FAIL: do NOT update stage.txt. Surface blockers for resolution.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

